feat: improve skill scores for agent-toolkit#20
Open
popey wants to merge 1 commit intosoftaworks:mainfrom
Open
feat: improve skill scores for agent-toolkit#20popey wants to merge 1 commit intosoftaworks:mainfrom
popey wants to merge 1 commit intosoftaworks:mainfrom
Conversation
Hullo @leonardocouy 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements. Here's the before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | ship-learn-next | 0% | 95% | +95% | | humanizer | 0% | 89% | +89% | | domain-name-brainstormer | 34% | 100% | +66% | | naming-analyzer | 45% | 100% | +55% | | qa-test-planner | 50% | 100% | +50% | | design-system-starter | 39% | 85% | +46% | | requirements-clarity | 63% | 96% | +33% | | agent-md-refactor | 76% | 100% | +24% | | gepetto | 76% | 100% | +24% | | reducing-entropy | 80% | 100% | +20% | | codex | 77% | 96% | +19% | | skill-judge | 73% | 93% | +20% | | web-to-markdown | 81% | 100% | +19% | | dependency-updater | 76% | 93% | +17% | | database-schema-designer | 76% | 93% | +17% | | c4-architecture | 86% | 100% | +14% | | game-changing-features | 80% | 93% | +13% | | gemini | 76% | 89% | +13% | | professional-communication | 81% | 93% | +12% | | react-useeffect | 88% | 100% | +12% | | writing-clearly-and-concisely | 84% | 96% | +12% | | marp-slide | 89% | 100% | +11% | | crafting-effective-readmes | 84% | 93% | +9% | | frontend-to-backend-requirements | 80% | 89% | +9% | | openapi-to-typescript | 83% | 89% | +6% | | excalidraw | 84% | 89% | +5% | | difficult-workplace-conversations | 88% | 93% | +5% | | daily-meeting-update | 89% | 93% | +4% | | backend-to-frontend-handoff-docs | 84% | 86% | +2% | <details> <summary>Changes made</summary> **Validation fixes (0% skills)** - `humanizer` / `ship-learn-next`: Fixed `allowed-tools` from YAML array to comma-separated string (validation failure blocked all scoring). Also removed unknown `version` frontmatter key. **Description improvements (most skills)** - Added explicit "Use when..." clauses with natural trigger terms users would actually say - Added specific concrete actions to descriptions (not just generic capability statements) - Improved distinctiveness to reduce conflict risk with similar skills **Content improvements** - Removed verbose explanations of concepts Claude already knows (semantic versioning, database normalization, QA fundamentals, design system philosophy, etc.) - Consolidated redundant sections (duplicate warnings, overlapping rules, repeated examples) - Added validation checkpoints to workflows where missing - Added concrete before/after code examples (react-useeffect, writing-clearly-and-concisely) - Restructured bloated skills into concise workflows (domain-name-brainstormer: 213→72 lines, qa-test-planner: 758→278 lines, naming-analyzer: 352→117 lines, skill-judge: 753→261 lines) **Progressive disclosure** - Extracted heavy reference content to separate files where it improved token efficiency (skill-judge references, daily-meeting-update examples, game-changing-features categories) </details> Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch - just saw room for improvement and wanted to contribute. If you want to run reviews, evals and optimizations yourself, just `npm install @tessl/cli` then run `tessl skill review path/to/your/SKILL.md`, and click [here](https://tessl.io/registry/skills/submit) to find out more. Thanks in advance 🙏
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hullo @leonardocouy 👋
I ran your skills through
tessl skill reviewat work and found some targeted improvements. Here's the ten with the most improvements:Here's the full before/after in text form:
Changes made
Validation fixes (0% skills)
humanizer/ship-learn-next: Fixedallowed-toolsfrom YAML array to comma-separated string (validation failure blocked all scoring). Also removed unknownversionfrontmatter key.Description improvements (most skills)
Content improvements
Progressive disclosure
Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch - just saw room for improvement and wanted to contribute.
Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at this Tessl guide and ask it to optimize your skill. Ping me - @popey - if you hit any snags.
Thanks in advance 🙏